噪声图引导：基于空间上下文的真实图像编辑反演方法
Noise Map Guidance: Inversion with Spatial Context for Real Image Editing
AI总结：
针对文本引导扩散模型编辑真实图像时重建质量下降的问题，提出噪声图引导（NMG）反演方法，无需优化即可保留空间上下文，提升编辑保真度，并兼容多种编辑技术。
摘要：
文本引导的扩散模型已成为图像合成中的流行工具，以其生成高质量、多样化图像的能力而闻名。然而，将其应用于真实图像编辑时，常遇到主要障碍，即文本条件会降低重建质量，进而影响编辑保真度。空文本反演（NTI）在该领域取得了进展，但它未能捕捉空间上下文，且需要计算密集的每时间步优化。针对这些挑战，我们提出了噪声图引导（NMG），一种富含空间上下文的反演方法，专为真实图像编辑设计。重要的是，NMG无需优化即可实现这一点，同时保持编辑质量。我们的实证研究凸显了NMG在各种编辑技术上的适应性，以及其对DDIM反演变体的鲁棒性。
英文摘要：
Text-guided diffusion models have become a popular tool in image synthesis, known for producing high-quality and diverse images. However, their application to editing real images often encounters hurdles primarily due to the text condition deteriorating the reconstruction quality and subsequently affecting editing fidelity. Null-text Inversion (NTI) has made strides in this area, but it fails to capture spatial context and requires computationally intensive per-timestep optimization. Addressing these challenges, we present Noise Map Guidance (NMG), an inversion method rich in a spatial context, tailored for real-image editing. Significantly, NMG achieves this without necessitating optimization, yet preserves the editing quality. Our empirical investigations highlight NMG's adaptability across various editing techniques and its robustness to variants of DDIM inversions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
